{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/non-adversarial-unsupervised-word-translation","title":"Non-Adversarial Unsupervised Word Translation","arxiv_id":"1801.06126","date":"2018-01-18","proceeding":"EMNLP 2018 10","authors":["Yedid Hoshen","Lior Wolf"],"abstract":"Unsupervised word translation from non-parallel inter-lingual corpora has\nattracted much research interest. Very recently, neural network methods trained\nwith adversarial loss functions achieved high accuracy on this task. Despite\nthe impressive success of the recent techniques, they suffer from the typical\ndrawbacks of generative adversarial models: sensitivity to hyper-parameters,\nlong training time and lack of interpretability. In this paper, we make the\nobservation that two sufficiently similar distributions can be aligned\ncorrectly with iterative matching methods. We present a novel method that first\naligns the second moment of the word distributions of the two languages and\nthen iteratively refines the alignment. Extensive experiments on word\ntranslation of European and Non-European languages show that our method\nachieves better performance than recent state-of-the-art deep adversarial\napproaches and is competitive with the supervised baseline. It is also\nefficient, easy to parallelize on CPU and interpretable.","url_abs":"http://arxiv.org/abs/1801.06126v3","url_pdf":"http://arxiv.org/pdf/1801.06126v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/facebookresearch/MUSE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/facebookresearch/Non-adversarialTranslation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/grtzsohalf/Audio-Phonetic-and-Semantic-Embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/jiajunhua/facebookresearch-MUSE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.06126","atlas_url":"https://app.syntology.ai/?focus=1801.06126","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}